{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T18:01:45Z","timestamp":1793901705563,"version":"4.8.0"},"reference-count":41,"publisher":"IOP Publishing","issue":"8","license":[{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01 EB028324"],"award-info":[{"award-number":["R01 EB028324"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Cancer Institute","award":["R01CA279013"],"award-info":[{"award-number":["R01CA279013"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2024,4,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which impairs its accuracy for dose verification. In this study, we developed a hybrid-supervised deep learning method for protoacoustic imaging to address the limited view issue.\n                    <jats:italic>Approach<\/jats:italic>\n                    . We proposed a Recon-Enhance two-stage deep learning method. In the Recon-stage, a transformer-based network was developed to reconstruct initial pressure maps from raw acoustic signals. The network is trained in a hybrid-supervised approach, where it is first trained using supervision by the iteratively reconstructed pressure map and then fine-tuned using transfer learning and self-supervision based on the data fidelity constraint. In the enhance-stage, a 3D U-net is applied to further enhance the image quality with supervision from the ground truth pressure map. The final protoacoustic images are then converted to dose for proton verification.\n                    <jats:italic>Main results<\/jats:italic>\n                    . The results evaluated on a dataset of 126 prostate cancer patients achieved an average root mean squared errors (RMSE) of 0.0292, and an average structural similarity index measure (SSIM) of 0.9618, out-performing related start-of-the-art methods. Qualitative results also demonstrated that our approach addressed the limit-view issue with more details reconstructed. Dose verification achieved an average RMSE of 0.018, and an average SSIM of 0.9891. Gamma index evaluation demonstrated a high agreement (94.7% and 95.7% for 1%\/3 mm and 1%\/5 mm) between the predicted and the ground truth dose maps. Notably, the processing time was reduced to 6 s, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.\n                    <jats:italic>Significance<\/jats:italic>\n                    . Our study achieved start-of-the-art performance in the challenging task of direct reconstruction from radiofrequency signals, demonstrating the great promise of PA imaging as a highly efficient and accurate tool for\n                    <jats:italic>in<\/jats:italic>\n                    <jats:italic>vivo<\/jats:italic>\n                    3D proton dose verification to minimize the range uncertainties of proton therapy to improve its precision and outcomes.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ad3327","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:42:20Z","timestamp":1710268940000},"page":"085007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Hybrid-supervised deep learning for domain transfer 3D protoacoustic image reconstruction"],"prefix":"10.1088","volume":"69","author":[{"given":"Yankun","family":"Lang","sequence":"first","affiliation":[{"name":"University of Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoran","family":"Jiang","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leshan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangzhong","family":"Xiang","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ren","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,4,3]]},"reference":[{"key":"pmbad3327bib1","doi-asserted-by":"publisher","first-page":"5735","DOI":"10.1118\/1.4929939","type":"journal-article","article-title":"Theoretical detection threshold of the proton-acoustic range verification technique","volume":"42","author":"Ahmad","year":"2015","journal-title":"Med. Phys."},{"key":"pmbad3327bib2","doi-asserted-by":"publisher","first-page":"5473","DOI":"10.1088\/0031-9155\/57\/17\/5473","type":"journal-article","article-title":"Effect of tissue heterogeneity on an in vivo range verification technique for proton therapy","volume":"57","author":"Bentefour","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib3","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab7506","type":"journal-article","article-title":"Proton range verification with ultrasound imaging using injectable radiation sensitive nanodroplets: a feasibility study","volume":"65","author":"Carlier","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib4","doi-asserted-by":"publisher","first-page":"2912","DOI":"10.1109\/TMI.2022.3175529","type":"journal-article","article-title":"Sam's net: aself-augmented multi-stage deep-learning network for end-to-end reconstruction of limited angle CT","volume":"41","author":"Chen","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad3327bib5","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/TMI.2018.2805692","type":"journal-article","article-title":"LEARN: Learned experts\u2019 assessment-based reconstruction network for sparse-data CT","volume":"37","author":"Chen","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad3327bib6","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaa203","type":"journal-article","article-title":"3D prompt gamma imaging for proton beam range verification","volume":"63","author":"Draeger","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib7","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1080\/02841860701769743","type":"journal-article","article-title":"In-beam PET measurements of biological half-lives of 12C irradiation induced \u03b2 \u00b1 activity","volume":"47","author":"Fiedler","year":"2008","journal-title":"Acta Oncol."},{"key":"pmbad3327bib8","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1088\/0031-9155\/55\/7\/013","type":"journal-article","article-title":"On the effectiveness of ion range determination from in-beam PET data","volume":"55","author":"Fiedler","year":"2010","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.pacs.2021.100240","type":"journal-article","article-title":"Dictionary-based protoacoustic dose map imaging for proton range verification","volume":"21","author":"Freijo","year":"2021","journal-title":"Photoacoustics"},{"key":"pmbad3327bib10","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.media.2019.03.013","type":"journal-article","article-title":"DeepPET: a deep encoder-decoder network for directly solving the PET image reconstruction inverse problem","volume":"54","author":"H\u00e4ggstr\u00f6m","year":"2019","journal-title":"Med. Imag. Anal."},{"key":"pmbad3327bib11","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/24\/5\/055006","type":"journal-article","article-title":"Reconstruction and time reversal in thermoacoustic tomography in acoustically homogeneous and inhomogeneous media","volume":"24","author":"Hristova","year":"2008","journal-title":"Inverse Prob."},{"key":"pmbad3327bib12","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC48229.2022.9871475","type":"preprint","article-title":"Fast MRI Reconstruction: how powerful transformers are?","author":"Huang","year":"2022"},{"key":"pmbad3327bib13","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.1109\/TMI.2019.2912791","type":"journal-article","article-title":"Augmentation of CBCT reconstructed from under-sampled projections using deep learning","volume":"38","author":"Jiang","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad3327bib14","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac9881","type":"journal-article","article-title":"3D in vivo dose verification in prostate proton therapy with deep learning-based proton-acoustic imaging","volume":"67","author":"Jiang","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib15","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.nima.2010.10.031","type":"journal-article","article-title":"A compton imager for in vivo dosimetry of proton beams design study\u201d, nuclear instruments and methods in physics research section a: accelerators, spectrometers","volume":"626","author":"Kormoll","year":"2011","journal-title":"Detectors Associated Equipment"},{"key":"pmbad3327bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.pacs.2020.100197","type":"journal-article","article-title":"Y-Net: hybrid deep learning image reconstruction for photoacoustic tomography in vivo","volume":"20","author":"Lan","year":"2020","journal-title":"Photoacoustics"},{"key":"pmbad3327bib17","first-page":"10012","type":"other","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"pmbad3327bib18","doi-asserted-by":"publisher","first-page":"5858","DOI":"10.1118\/1.3504609","type":"journal-article","article-title":"Investigation of an implantable dosimeter for single-point water equivalent path length verification in proton therapy","volume":"37","author":"Lu","year":"2010","journal-title":"Med. Phys."},{"key":"pmbad3327bib19","first-page":"276","type":"other","article-title":"3D transformer-GAN for high-quality PET reconstruction","author":"Luo","year":"2021"},{"key":"pmbad3327bib20","article-title":"Is it time to replace cnns with transformers for medical images?","author":"Matsoukas","year":"2021","type":"preprint"},{"key":"pmbad3327bib21","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1118\/1.3694098","type":"journal-article","article-title":"Development of array-type prompt gamma measurement system for in vivo range verification in proton therapy","volume":"39","author":"Min","year":"2012","journal-title":"Med. Phys."},{"key":"pmbad3327bib22","doi-asserted-by":"publisher","first-page":"4445","DOI":"10.1118\/1.3462559","type":"journal-article","article-title":"Measurement and verification of positron emitter nuclei generated at each treatment site by target nuclear fragment reactions in proton therapy","volume":"37","author":"Miyatake","year":"2010","journal-title":"Med. Phys."},{"key":"pmbad3327bib23","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.ijrobp.2009.05.065","type":"journal-article","article-title":"The development and clinical use of a beam ON-LINE PET system mounted on a rotating gantry port in proton therapy","volume":"76","author":"Nishio","year":"2010","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"pmbad3327bib24","first-page":"4055","type":"other","article-title":"Image transformer","author":"Parmar","year":"2018"},{"key":"pmbad3327bib25","doi-asserted-by":"publisher","first-page":"4511","DOI":"10.1118\/1.3218759","type":"journal-article","article-title":"A more accurate reconstruction system matrix for quantitative proton computed tomography","volume":"36","author":"Penfold","year":"2009","journal-title":"Med. Phys."},{"key":"pmbad3327bib26","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1002\/mp.15975","type":"journal-article","article-title":"Automatic detection and classification of treatment deviations in proton therapy from realistically simulated prompt gamma imaging data","volume":"50","author":"Pietsch","year":"2023","journal-title":"Med. Phys."},{"key":"pmbad3327bib27","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1088\/0031-9155\/54\/3\/017","type":"journal-article","article-title":"Prompt gamma-ray emission from biological tissues during proton irradiation: a preliminary study","volume":"54","author":"Polf","year":"2009","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib28","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.zemedi.2011.06.001","type":"journal-article","article-title":"Spatial resolution of proton tomography: methods, initial phase space and object thickness","volume":"22","author":"Schneider","year":"2012","journal-title":"Z. Med. Phys."},{"key":"pmbad3327bib29","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1118\/1.1690713","type":"journal-article","article-title":"First proton radiography of an animal patient","volume":"31","author":"Schneider","year":"2004","journal-title":"Med. Phys."},{"key":"pmbad3327bib30","doi-asserted-by":"publisher","first-page":"7957","DOI":"10.1088\/0031-9155\/57\/23\/7957","type":"journal-article","article-title":"Quantitative carbon ion beam radiography and tomography with a flat-panel detector","volume":"57","author":"Telsemeyer","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"pmbad3327bib31","doi-asserted-by":"publisher","DOI":"10.1117\/1.3360308","type":"journal-article","article-title":"k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields","volume":"15","author":"Treeby","year":"2010","journal-title":"J. Biomed. Opt."},{"key":"pmbad3327bib32","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/26\/11\/115003","type":"journal-article","article-title":"Photoacoustic tomography in absorbing acoustic media using time reversal","volume":"26","author":"Treeby","year":"2010","journal-title":"Inverse Prob."},{"key":"pmbad3327bib33","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/TRPMS.2020.3015109","type":"journal-article","article-title":"Toward in vivo dosimetry for prostate radiotherapy with a transperineal ultrasound array: a simulation study","volume":"5","author":"Wang","year":"2020","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"pmbad3327bib34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.71.016706","type":"journal-article","article-title":"Universal back-projection algorithm for photoacoustic computed tomography","volume":"71","author":"Xu","year":"2005","journal-title":"Phys. Rev. E"},{"key":"pmbad3327bib35","type":"journal-article","article-title":"Further investigation of 3D dose verification in proton therapy utilizing acoustic signal, wavelet decomposition and machine learning","volume":"8","author":"Yao","year":"2021","journal-title":"Biomed. Phys. Eng. Express"},{"key":"pmbad3327bib36","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/TUFFC.2019.2942557","type":"journal-article","article-title":"Design of a volumetric imaging sequence using a vantage-256 ultrasound research platform multiplexed with a 1024-element fully sampled matrix array","volume":"67","author":"Yu","year":"2019a","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbad3327bib37","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.1002\/mp.13661","type":"journal-article","article-title":"Simulation studies of time reversal-based protoacoustic reconstruction for range and dose verification in proton therapy","volume":"46","author":"Yu","year":"2019b","journal-title":"Med. Phys."},{"key":"pmbad3327bib38","doi-asserted-by":"publisher","first-page":"4485","DOI":"10.1002\/mp.15046","type":"journal-article","article-title":"Feasibility study of 3D time-reversal reconstruction of proton-induced acoustic signals for dose verification in the head and the liver: a simulation study","volume":"48","author":"Yu","year":"2021","journal-title":"Med. Phys."},{"key":"pmbad3327bib39","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.radonc.2013.01.016","type":"journal-article","article-title":"Feasibility study of in vivo MRI based dosimetric verification of proton end-of-range for liver cancer patients","volume":"106","author":"Yuan","year":"2013","journal-title":"Radiother. Oncol."},{"key":"pmbad3327bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102018","type":"journal-article","article-title":"Ultrasound image reconstruction from plane wave radio-frequency data by self-supervised deep neural network","volume":"70","author":"Zhang","year":"2021","journal-title":"Med. Image Anal."},{"key":"pmbad3327bib41","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/nature25988","type":"journal-article","article-title":"Image reconstruction by domain-transform manifold learning","volume":"555","author":"Zhu","year":"2018","journal-title":"Nature"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:05:33Z","timestamp":1778778333000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad3327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,3]]},"references-count":41,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,4,3]]},"published-print":{"date-parts":[[2024,4,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad3327","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,3]]},"assertion":[{"value":"Hybrid-supervised deep learning for domain transfer 3D protoacoustic image reconstruction","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2023-07-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-03-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-04-03","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}